Political polling relies heavily on sampling techniques, which allow us to make inferences about an entire population based on only a portion of the population. However, the "Brexit" referendum in the United Kingdom and several elections in the United States since 2016 have called into question the accuracy of much political polling.

1. What explains the inaccuracy of many pre-election polling data since 2016? Provide specific case examples.

2. What statistical techniques could be used to improve the accuracy of polling?

3. Has the value of political polling diminished? What is your personal perception of political polling?